Triple
T16583670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yixian |
E402898
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Chengkan |
E1220962
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Chengkan | Statement: [Yixian, contains, Chengkan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chengkan Context triple: [Yixian, contains, Chengkan]
-
A.
Chengkan
chosen
Chengkan is a historic, well-preserved ancient village in Anhui Province, China, known for its traditional Huizhou architecture and cultural heritage.
-
B.
Yasakaji
Yasakaji is a Buddhist temple in Japan known as Temple 47 on the Shikoku Pilgrimage.
-
C.
Nouchi
Nouchi is an Ivorian urban slang and lingua franca that blends French with local African languages and is widely spoken in Abidjan and other parts of Côte d’Ivoire.
-
D.
Kōtaishi
Kōtaishi is the formal Japanese title used to designate the heir apparent to the Chrysanthemum Throne.
-
E.
Gaochi
Gaochi is the given name of Zhu Gaochi, the Ming dynasty emperor known posthumously as the Hongxi Emperor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35999f80c8190852fd4137bc45a80 |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007597905881909df7dc49961b6a02 |
completed | May 10, 2026, 12:09 p.m. |
Created at: April 10, 2026, 5:16 a.m.